© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57903
    Prev
    Next
    INDEX
    Explanations

    class name declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noon
    -0.08
    sealed
    -0.07
    der
    -0.07
    .MouseAdapter
    -0.07
    SID
    -0.07
    SY
    -0.07
    票
    -0.07
    oul
    -0.07
     Pound
    -0.07
    vt
    -0.07
    POSITIVE LOGITS
    ards
    0.09
    hy
    0.09
     Gould
    0.09
     Duel
    0.09
    neider
    0.09
     pH
    0.09
    ê·
    0.09
    ĵį
    0.09
     abs
    0.09
     crush
    0.08
    Activations Density 0.012%

    No Known Activations